# On the Geometric Accuracy of Implicit and Primitive-based Representations Derived from View Rendering Constraints

arXiv: https://arxiv.org/abs/2509.10241 · HTML: https://mlsanity.com/paper/2509.10241/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [A Survey of Structure from Motion](https://mlsanity.com/paper/1701.08493/) (2017)
- [WildGaussians: 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2407.08447/) (2024)
- [LoopSplat: Loop Closure by Registering 3D Gaussian Splats](https://mlsanity.com/paper/2408.10154/) (2024)
- [SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap](https://mlsanity.com/paper/2110.03101/) (2021)
- [3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes](https://mlsanity.com/paper/2411.14974/) (2024)
- [Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing](https://mlsanity.com/paper/2403.10050/) (2024)
- [Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Review](https://mlsanity.com/paper/2405.03417/) (2024)
- [Textured Gaussians for Enhanced 3D Scene Appearance Modeling](https://mlsanity.com/paper/2411.18625/) (2024)
- [GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling](https://mlsanity.com/paper/2409.12954/) (2024)
- [Vision-based Neural Scene Representations for Spacecraft](https://mlsanity.com/paper/2105.06405/) (2021)
- [3D Reconstruction of Non-cooperative Resident Space Objects using Instant NGP-accelerated NeRF and D-NeRF](https://mlsanity.com/paper/2301.09060/) (2023)
- [Leveraging Neural Radiance Fields for Pose Estimation of an Unknown Space Object during Proximity Operations](https://mlsanity.com/paper/2405.12728/) (2024)

## Built on by (most cited first, 1 of 1)

- [NeRF-based Spacecraft Reconstruction from Monocular Imagery Under Illumination Variability and Pose Uncertainty](https://mlsanity.com/paper/2605.18447/) (2026)

## Abstract (arXiv)

We present the first systematic comparison of implicit and explicit Novel View Synthesis methods for space-based 3D object reconstruction, evaluating the role of appearance embeddings. While embeddings improve photometric fidelity by modeling lighting variation, we show they do not translate into meaningful gains in geometric accuracy - a critical requirement for space robotics applications. Using the SPEED+ dataset, we compare K-Planes, Gaussian Splatting, and Convex Splatting, and demonstrate that embeddings primarily reduce the number of primitives needed for explicit methods rather than enhancing geometric fidelity. Moreover, convex splatting achieves more compact and clutter-free representations than Gaussian splatting, offering advantages for safety-critical applications such as interaction and collision avoidance. Our findings clarify the limits of appearance embeddings for geometry-centric tasks and highlight trade-offs between reconstruction quality and representation efficiency in space scenarios.